# DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2207.03081 · HTML: https://mlsanity.com/paper/2207.03081/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 7 Jul 2022.

## Builds on (most cited first, 29 of 29)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)
- [Soft Actor-Critic for Discrete Action Settings](https://mlsanity.com/paper/1910.07207/) (2019)
- [Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline](https://mlsanity.com/paper/2004.01179/) (2020)
- [Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels](https://mlsanity.com/paper/1903.12529/) (2019)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [State Entropy Maximization with Random Encoders for Efficient Exploration](https://mlsanity.com/paper/2102.09430/) (2021)
- [ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content](https://mlsanity.com/paper/1803.02266/) (2018)
- [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018)
- [Deep White-Balance Editing](https://mlsanity.com/paper/2004.01354/) (2020)
- [Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning](https://mlsanity.com/paper/1804.03312/) (2018)
- [CameraNet: A Two-Stage Framework for Effective Camera ISP Learning](https://mlsanity.com/paper/1908.01481/) (2019)
- [AWNet: Attentive Wavelet Network for Image ISP](https://mlsanity.com/paper/2008.09228/) (2020)
- [Reconfiguring the Imaging Pipeline for Computer Vision](https://mlsanity.com/paper/1705.04352/) (2017)
- [Exposure: A White-Box Photo Post-Processing Framework](https://mlsanity.com/paper/1709.09602/) (2017)
- [Automatic ISP image quality tuning using non-linear optimization](https://mlsanity.com/paper/1902.09023/) (2019)
- [An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search](https://mlsanity.com/paper/2012.05417/) (2020)
- [Camera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessment](https://mlsanity.com/paper/1907.12646/) (2019)
- [Learning a Reinforced Agent for Flexible Exposure Bracketing Selection](https://mlsanity.com/paper/2005.12536/) (2020)
- [Learning Multi-Scale Photo Exposure Correction](https://mlsanity.com/paper/2003.11596/) (2020)
- [Learning Adaptive Parameter Tuning for Image Processing](https://mlsanity.com/paper/1610.09414/) (2016)

## Built on by (most cited first, 4 of 4)

- [Learning to Control Camera Exposure via Reinforcement Learning](https://mlsanity.com/paper/2404.01636/) (2024)
- [ATTIQA: Generalizable Image Quality Feature Extractor using Attribute-aware Pretraining](https://mlsanity.com/paper/2406.01020/) (2024)
- [POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP](https://mlsanity.com/paper/2604.06938/) (2026)
- [Dual-Exposure Imaging with Events](https://mlsanity.com/paper/2604.10273/) (2026)

## Abstract (arXiv)

In this paper, we propose a multi-objective camera ISP framework that utilizes Deep Reinforcement Learning (DRL) and camera ISP toolbox that consist of network-based and conventional ISP tools. The proposed DRL-based camera ISP framework iteratively selects a proper tool from the toolbox and applies it to the image to maximize a given vision task-specific reward function. For this purpose, we implement total 51 ISP tools that include exposure correction, color-and-tone correction, white balance, sharpening, denoising, and the others. We also propose an efficient DRL network architecture that can extract the various aspects of an image and make a rigid mapping relationship between images and a large number of actions. Our proposed DRL-based ISP framework effectively improves the image quality according to each vision task such as RAW-to-RGB image restoration, 2D object detection, and monocular depth estimation.